@inproceedings{meem-etal-2024-pat,
title = "{PAT}-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering",
author = "Meem, Jannat and
Rashid, Muhammad and
Dong, Yue and
Hristidis, Vagelis",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.777",
pages = "13129--13148",
abstract = "Existing work on Temporal Question Answering (TQA) has predominantly focused on questions anchored to specific timestamps or events (e.g. {`}Who was the US president in 1970?{'}). Little work has studied questions whose temporal context is relative to the present time (e.g. {`}Who was the previous US president?{'}). We refer to this problem as Present-Anchored Temporal QA (PATQA). PATQA poses unique challenges: (1) large language models (LLMs) may have outdated knowledge, (2) complex temporal relationships (e.g. {`}before{'}, {`}previous{'}) are hard to reason, (3) multi-hop reasoning may be required, and (4) the gold answers of benchmarks must be continuously updated. To address these challenges, we introduce the PAT-Questions benchmark, which includes single and multi-hop temporal questions. The answers in PAT-Questions can be automatically refreshed by re-running SPARQL queries on a knowledge graph, if available. We evaluate several state-of-the-art LLMs and a SOTA temporal reasoning model (TEMPREASON-T5) on PAT-Questions through direct prompting and retrieval-augmented generation (RAG). The results highlight the limitations of existing solutions in PATQA and motivate the need for new methods to improve PATQA reasoning capabilities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meem-etal-2024-pat">
<titleInfo>
<title>PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jannat</namePart>
<namePart type="family">Meem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vagelis</namePart>
<namePart type="family">Hristidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing work on Temporal Question Answering (TQA) has predominantly focused on questions anchored to specific timestamps or events (e.g. ‘Who was the US president in 1970?’). Little work has studied questions whose temporal context is relative to the present time (e.g. ‘Who was the previous US president?’). We refer to this problem as Present-Anchored Temporal QA (PATQA). PATQA poses unique challenges: (1) large language models (LLMs) may have outdated knowledge, (2) complex temporal relationships (e.g. ‘before’, ‘previous’) are hard to reason, (3) multi-hop reasoning may be required, and (4) the gold answers of benchmarks must be continuously updated. To address these challenges, we introduce the PAT-Questions benchmark, which includes single and multi-hop temporal questions. The answers in PAT-Questions can be automatically refreshed by re-running SPARQL queries on a knowledge graph, if available. We evaluate several state-of-the-art LLMs and a SOTA temporal reasoning model (TEMPREASON-T5) on PAT-Questions through direct prompting and retrieval-augmented generation (RAG). The results highlight the limitations of existing solutions in PATQA and motivate the need for new methods to improve PATQA reasoning capabilities.</abstract>
<identifier type="citekey">meem-etal-2024-pat</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.777</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13129</start>
<end>13148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering
%A Meem, Jannat
%A Rashid, Muhammad
%A Dong, Yue
%A Hristidis, Vagelis
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F meem-etal-2024-pat
%X Existing work on Temporal Question Answering (TQA) has predominantly focused on questions anchored to specific timestamps or events (e.g. ‘Who was the US president in 1970?’). Little work has studied questions whose temporal context is relative to the present time (e.g. ‘Who was the previous US president?’). We refer to this problem as Present-Anchored Temporal QA (PATQA). PATQA poses unique challenges: (1) large language models (LLMs) may have outdated knowledge, (2) complex temporal relationships (e.g. ‘before’, ‘previous’) are hard to reason, (3) multi-hop reasoning may be required, and (4) the gold answers of benchmarks must be continuously updated. To address these challenges, we introduce the PAT-Questions benchmark, which includes single and multi-hop temporal questions. The answers in PAT-Questions can be automatically refreshed by re-running SPARQL queries on a knowledge graph, if available. We evaluate several state-of-the-art LLMs and a SOTA temporal reasoning model (TEMPREASON-T5) on PAT-Questions through direct prompting and retrieval-augmented generation (RAG). The results highlight the limitations of existing solutions in PATQA and motivate the need for new methods to improve PATQA reasoning capabilities.
%U https://aclanthology.org/2024.findings-acl.777
%P 13129-13148
Markdown (Informal)
[PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering](https://aclanthology.org/2024.findings-acl.777) (Meem et al., Findings 2024)
ACL